OPO qwen2-0.5b
Collection
5 items
•
Updated
qwen2-0.5b-neural_ndcg-listsize_8-tau_0.1-beta_0.05-batchsize_128
This model is a fine-tuned version of yangzhao02/qwen2-0.5b-sft on the yangzhao02/ListUltraFeedback dataset. It achieves the following results on the evaluation set:
- Loss: -0.9830
- Logps: -367.2024
- Logits: -2.4986
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-07
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Logps | Logits |
|---|---|---|---|---|---|
| -0.9822 | 0.4275 | 200 | -0.9821 | -365.9305 | -2.5253 |
| -0.9831 | 0.8550 | 400 | -0.9830 | -367.2024 | -2.4986 |
Framework versions
- Transformers 4.42.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 2
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.